Wolfe-Jam

Slash Nextjs — AI skill for Claude Code

AI community

Token-optimized AI chat.

How to install Slash Nextjs

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Wolfe-Jam/slash-nextjs and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Slash Nextjs does

Token-optimized AI chat. Next.js + Vercel AI SDK + slash-tokens/auto. One import. Every call optimized.

Alternatives in AI

Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
Axonhub — ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs 3.2k ★
Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★

README

slash-nextjs — Token-Optimized AI Starter

[![CI/CD](https://github.com/Wolfe-Jam/slash-nextjs/actions/workflows/test.yml/badge.svg?branch=main)](https://github.com/Wolfe-Jam/slash-nextjs/actions/workflows/test.yml) [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/Wolfe-Jam/slash-nextjs&project-name=slash-nextjs&repository-name=slash-nextjs&env=ANTHROPIC_API_KEY&envDescription=Any+one+provider+key+works+-+Anthropic,+OpenAI,+xAI+or+Google.+See+.env.example+for+all+options.&envLink=https://github.com/Wolfe-Jam/slash-nextjs/blob/main/.env.example) [![⭐ Star on GitHub](https://img.shields.io/badge/%E2%AD%90_Star-black?logo=github&logoColor=white)](https://github.com/Wolfe-Jam/slash-nextjs)

**See it work:** [slash-nextjs-wofejams-projects.vercel.app](https://slash-nextjs-wofejams-projects.vercel.app) — a live chat. Every LLM call through the Slash gate before it leaves the server. Then `bunx slash-tokens`, [get a key](https://mcpaas.live/slash/setup) ($20 on the house), or [Team — $39 for the data](https://slashtokens.com).

This repo is the demo behind that chat, not a starter to fork. If you do clone it, the deploy shows a generic green+gold placeholder ("Token Saver"). Slash's identity is gated — see [License](#license).

One proxy. One config line. Three outcomes:

Prevent — empty, duplicate, trivial, context overflow, or rapid-fire calls blocked. $0 spent.
Re-route — cheaper model in the same family fits? Opus 4.7 → Haiku. GPT-5.4 → Nano. Grok-4.20 → Fast. Same answer, 80-95% less.
Pass — right model, right cost? Let it fly.

4.8 KB WASM · sub-millisecond decision · zero added dependencies.

slash-nextjs demo

Why

Most Next.js AI apps default to a frontier model for everything. A simple query on Opus 4.7 can cost 5–10x more than on Haiku — for the same answer. Slash decides pre-call, not after the invoice